def setup_images(path=None,
series=None,
offset=None,
size=None,
proc_mode=None,
allow_import=True):
"""Sets up an image and all associated images and metadata.
Paths for related files such as registered images will generally be
constructed from ``path``. If :attr:`config.prefix` is set, it will
be used in place of ``path`` for registered labels.
Args:
path (str): Path to image from which MagellanMapper-style paths will
be generated.
series (int): Image series number; defaults to None.
offset (List[int]): Sub-image offset given in z,y,x; defaults to None.
size (List[int]): Sub-image shape given in z,y,x; defaults to None.
proc_mode (str): Processing mode, which should be a key in
:class:`config.ProcessTypes`, case-insensitive; defaults to None.
allow_import (bool): True to allow importing the image if it
cannot be loaded; defaults to True.
"""
def add_metadata():
# override metadata set from command-line metadata args if available
md = {
config.MetaKeys.RESOLUTIONS:
config.meta_dict[config.MetaKeys.RESOLUTIONS],
config.MetaKeys.MAGNIFICATION:
config.meta_dict[config.MetaKeys.MAGNIFICATION],
config.MetaKeys.ZOOM:
config.meta_dict[config.MetaKeys.ZOOM],
config.MetaKeys.SHAPE:
config.meta_dict[config.MetaKeys.SHAPE],
config.MetaKeys.DTYPE:
config.meta_dict[config.MetaKeys.DTYPE],
}
for key, val in md.items():
if val is not None:
# explicitly set metadata takes precedence over extracted vals
import_md[key] = val
# LOAD MAIN IMAGE
# reset image5d
config.image5d = None
config.image5d_is_roi = False
load_subimage = offset is not None and size is not None
config.resolutions = None
# reset label images
config.labels_img = None
config.borders_img = None
filename_base = importer.filename_to_base(path, series)
subimg_base = None
if load_subimage and not config.save_subimg:
# load a saved sub-image file if available and not set to save one
subimg_base = stack_detect.make_subimage_name(filename_base, offset,
size)
filename_subimg = libmag.combine_paths(subimg_base,
config.SUFFIX_SUBIMG)
try:
# load sub-image if available
config.image5d = np.load(filename_subimg, mmap_mode="r")
config.image5d = importer.roi_to_image5d(config.image5d)
config.image5d_is_roi = True
config.image5d_io = config.LoadIO.NP
print("Loaded sub-image from {} with shape {}".format(
filename_subimg, config.image5d.shape))
# after loading sub-image, load original image's metadata
# for essential data such as vmin/vmax; will only warn if
# fails to load since metadata could be specified elsewhere
_, orig_info = importer.make_filenames(path, series)
print("load original image metadata from:", orig_info)
importer.load_metadata(orig_info)
except IOError:
print("Ignored sub-image file from {} as unable to load".format(
filename_subimg))
proc_type = libmag.get_enum(proc_mode, config.ProcessTypes)
if proc_type in (config.ProcessTypes.LOAD, config.ProcessTypes.EXPORT_ROIS,
config.ProcessTypes.EXPORT_BLOBS,
config.ProcessTypes.DETECT):
# load a blobs archive
try:
if subimg_base:
try:
# load blobs generated from sub-image
config.blobs = load_blobs(subimg_base)
except (FileNotFoundError, KeyError):
# fallback to loading from full image blobs and getting
# a subset, shifting them relative to sub-image offset
print("Unable to load blobs file based on {}, will try "
"from {}".format(subimg_base, filename_base))
config.blobs = load_blobs(filename_base)
config.blobs, _ = detector.get_blobs_in_roi(config.blobs,
offset,
size,
reverse=False)
detector.shift_blob_rel_coords(config.blobs,
np.multiply(offset, -1))
else:
# load full image blobs
config.blobs = load_blobs(filename_base)
except (FileNotFoundError, KeyError) as e2:
print("Unable to load blobs file")
if proc_type in (config.ProcessTypes.LOAD,
config.ProcessTypes.EXPORT_BLOBS):
# blobs expected but not found
raise e2
if path and config.image5d is None:
# load or import the main image stack
print("Loading main image")
try:
if path.endswith(sitk_io.EXTS_3D):
# attempt to format supported by SimpleITK and prepend time axis
config.image5d = sitk_io.read_sitk_files(path)[None]
config.image5d_io = config.LoadIO.SITK
else:
# load or import from MagellanMapper Numpy format
import_only = proc_type is config.ProcessTypes.IMPORT_ONLY
if not import_only:
# load previously imported image
config.image5d = importer.read_file(path, series)
if allow_import:
# re-import over existing image or import new image
if os.path.isdir(path) and all(
[r is None for r in config.reg_suffixes.values()]):
# import directory of single plane images to single
# stack if no register suffixes are set
chls, import_md = importer.setup_import_dir(path)
add_metadata()
prefix = config.prefix
if not prefix:
prefix = os.path.join(
os.path.dirname(path),
importer.DEFAULT_IMG_STACK_NAME)
config.image5d = importer.import_planes_to_stack(
chls, prefix, import_md)
elif import_only or config.image5d is None:
# import multi-plane image
chls, import_path = importer.setup_import_multipage(
path)
prefix = config.prefix if config.prefix else import_path
import_md = importer.setup_import_metadata(
chls, config.channel, series)
add_metadata()
config.image5d = importer.import_multiplane_images(
chls,
prefix,
import_md,
series,
channel=config.channel)
config.image5d_io = config.LoadIO.NP
except FileNotFoundError as e:
print(e)
print("Could not load {}, will fall back to any associated "
"registered image".format(path))
if config.metadatas and config.metadatas[0]:
# assign metadata from alternate file if given to supersede settings
# for any loaded image5d
# TODO: access metadata directly from given image5d's dict to allow
# loading multiple image5d images simultaneously
importer.assign_metadata(config.metadatas[0])
# main image is currently required since many parameters depend on it
atlas_suffix = config.reg_suffixes[config.RegSuffixes.ATLAS]
if atlas_suffix is None and config.image5d is None:
# fallback to atlas if main image not already loaded
atlas_suffix = config.RegNames.IMG_ATLAS.value
print(
"main image is not set, falling back to registered "
"image with suffix", atlas_suffix)
# use prefix to get images registered to a different image, eg a
# downsampled version, or a different version of registered images
path = config.prefix if config.prefix else path
if path and atlas_suffix is not None:
try:
# will take the place of any previously loaded image5d
config.image5d = sitk_io.read_sitk_files(
path, reg_names=atlas_suffix)[None]
config.image5d_io = config.LoadIO.SITK
except FileNotFoundError as e:
print(e)
annotation_suffix = config.reg_suffixes[config.RegSuffixes.ANNOTATION]
if annotation_suffix is not None:
# load labels image, set up scaling, and load labels file
try:
# TODO: need to support multichannel labels images
config.labels_img = sitk_io.read_sitk_files(
path, reg_names=annotation_suffix)
if config.image5d is not None:
config.labels_scaling = importer.calc_scaling(
config.image5d, config.labels_img)
if config.load_labels is not None:
labels_ref = ontology.load_labels_ref(config.load_labels)
if isinstance(labels_ref, pd.DataFrame):
# parse CSV files loaded into data frame
config.labels_ref_lookup = ontology.create_lookup_pd(
labels_ref)
else:
# parse dict from ABA JSON file
config.labels_ref_lookup = (
ontology.create_aba_reverse_lookup(labels_ref))
except FileNotFoundError as e:
print(e)
borders_suffix = config.reg_suffixes[config.RegSuffixes.BORDERS]
if borders_suffix is not None:
# load borders image, which can also be another labels image
try:
config.borders_img = sitk_io.read_sitk_files(
path, reg_names=borders_suffix)
except FileNotFoundError as e:
print(e)
if (config.atlas_labels[config.AtlasLabels.ORIG_COLORS]
and config.load_labels is not None):
# load original labels image from same directory as ontology
# file for consistent ID-color mapping, even if labels are missing
try:
config.labels_img_orig = sitk_io.load_registered_img(
config.load_labels, config.RegNames.IMG_LABELS.value)
except FileNotFoundError as e:
print(e)
libmag.warn(
"could not load original labels image; colors may differ"
"differ from it")
load_rot90 = config.roi_profile["load_rot90"]
if load_rot90 and config.image5d is not None:
# rotate main image specified num of times x90deg after loading since
# need to rotate images output by deep learning toolkit
config.image5d = np.rot90(config.image5d, load_rot90, (2, 3))
if (config.image5d is not None and load_subimage
and not config.image5d_is_roi):
# crop full image to bounds of sub-image
config.image5d = plot_3d.prepare_subimg(config.image5d, size,
offset)[None]
config.image5d_is_roi = True
# add any additional image5d thresholds for multichannel images, such
# as those loaded without metadata for these settings
colormaps.setup_cmaps()
num_channels = get_num_channels(config.image5d)
config.near_max = libmag.pad_seq(config.near_max, num_channels, -1)
config.near_min = libmag.pad_seq(config.near_min, num_channels, 0)
config.vmax_overview = libmag.pad_seq(config.vmax_overview, num_channels)
colormaps.setup_colormaps(num_channels)
def setup_images(path: str,
series: Optional[int] = None,
offset: Optional[Sequence[int]] = None,
size: Optional[Sequence[int]] = None,
proc_type: Optional["config.ProcessTypes"] = None,
allow_import: bool = True,
fallback_main_img: bool = True):
"""Sets up an image and all associated images and metadata.
Paths for related files such as registered images will generally be
constructed from ``path``. If :attr:`config.prefix` is set, it will
be used in place of ``path`` for registered labels.
Args:
path: Path to image from which MagellanMapper-style paths will
be generated.
series: Image series number; defaults to None.
offset: Sub-image offset given in z,y,x; defaults to None.
size: Sub-image shape given in z,y,x; defaults to None.
proc_type: Processing type.
allow_import: True to allow importing the image if it
cannot be loaded; defaults to True.
fallback_main_img: True to fall back to loading a registered image
if possible if the main image could not be loaded; defaults to True.
"""
def add_metadata():
# override metadata set from command-line metadata args if available
md = {
config.MetaKeys.RESOLUTIONS:
config.meta_dict[config.MetaKeys.RESOLUTIONS],
config.MetaKeys.MAGNIFICATION:
config.meta_dict[config.MetaKeys.MAGNIFICATION],
config.MetaKeys.ZOOM:
config.meta_dict[config.MetaKeys.ZOOM],
config.MetaKeys.SHAPE:
config.meta_dict[config.MetaKeys.SHAPE],
config.MetaKeys.DTYPE:
config.meta_dict[config.MetaKeys.DTYPE],
}
for key, val in md.items():
if val is not None:
# explicitly set metadata takes precedence over extracted vals
import_md[key] = val
res = import_md[config.MetaKeys.RESOLUTIONS]
if res is None:
# default to 1 for x,y,z since image resolutions are required
res = [1] * 3
import_md[config.MetaKeys.RESOLUTIONS] = res
_logger.warn("No image resolutions found. Defaulting to: %s", res)
# LOAD MAIN IMAGE
# reset image5d
config.image5d = None
config.image5d_is_roi = False
config.img5d = Image5d()
load_subimage = offset is not None and size is not None
config.resolutions = None
# reset label images
config.labels_img = None
config.labels_img_sitk = None
config.labels_img_orig = None
config.borders_img = None
config.labels_meta = None
config.labels_ref = None
# reset blobs
config.blobs = None
filename_base = importer.filename_to_base(path, series)
subimg_base = None
blobs = None
# registered images set to load
atlas_suffix = config.reg_suffixes[config.RegSuffixes.ATLAS]
annotation_suffix = config.reg_suffixes[config.RegSuffixes.ANNOTATION]
borders_suffix = config.reg_suffixes[config.RegSuffixes.BORDERS]
if load_subimage and not config.save_subimg:
# load a saved sub-image file if available and not set to save one
subimg_base = naming.make_subimage_name(filename_base, offset, size)
filename_subimg = libmag.combine_paths(subimg_base,
config.SUFFIX_SUBIMG)
try:
# load sub-image if available
config.image5d = np.load(filename_subimg, mmap_mode="r")
config.image5d = importer.roi_to_image5d(config.image5d)
config.image5d_is_roi = True
config.img5d.img = config.image5d
config.img5d.path_img = filename_subimg
config.img5d.img_io = config.LoadIO.NP
config.img5d.subimg_offset = offset
config.img5d.subimg_size = size
print("Loaded sub-image from {} with shape {}".format(
filename_subimg, config.image5d.shape))
# after loading sub-image, load original image's metadata
# for essential data such as vmin/vmax; will only warn if
# fails to load since metadata could be specified elsewhere
_, orig_info = importer.make_filenames(path, series)
print("load original image metadata from:", orig_info)
importer.load_metadata(orig_info)
except IOError:
print("Ignored sub-image file from {} as unable to load".format(
filename_subimg))
if config.load_data[config.LoadData.BLOBS] or proc_type in (
config.ProcessTypes.LOAD, config.ProcessTypes.COLOC_MATCH,
config.ProcessTypes.EXPORT_ROIS, config.ProcessTypes.EXPORT_BLOBS):
# load a blobs archive
blobs = detector.Blobs()
try:
if subimg_base:
try:
# load blobs generated from sub-image
config.blobs = blobs.load_blobs(
img_to_blobs_path(subimg_base))
except (FileNotFoundError, KeyError):
# fallback to loading from full image blobs and getting
# a subset, shifting them relative to sub-image offset
print("Unable to load blobs file based on {}, will try "
"from {}".format(subimg_base, filename_base))
config.blobs = blobs.load_blobs(
img_to_blobs_path(filename_base))
blobs.blobs, _ = detector.get_blobs_in_roi(blobs.blobs,
offset,
size,
reverse=False)
detector.Blobs.shift_blob_rel_coords(
blobs.blobs, np.multiply(offset, -1))
else:
# load full image blobs
config.blobs = blobs.load_blobs(
img_to_blobs_path(filename_base))
except (FileNotFoundError, KeyError) as e2:
print("Unable to load blobs file")
if proc_type in (config.ProcessTypes.LOAD,
config.ProcessTypes.EXPORT_BLOBS):
# blobs expected but not found
raise e2
if path and config.image5d is None and not atlas_suffix:
# load or import the main image stack
print("Loading main image")
try:
path_lower = path.lower()
import_only = proc_type is config.ProcessTypes.IMPORT_ONLY
if path_lower.endswith(sitk_io.EXTS_3D):
# load format supported by SimpleITK and prepend time axis;
# if 2D, convert to 3D
img5d = sitk_io.read_sitk_files(path, make_3d=True)
elif not import_only and path_lower.endswith((".tif", ".tiff")):
# load TIF file directly
img5d, meta = read_tif(path)
config.resolutions = meta[config.MetaKeys.RESOLUTIONS]
else:
# load or import from MagellanMapper Numpy format
img5d = None
if not import_only:
# load previously imported image
img5d = importer.read_file(path, series)
if allow_import and (img5d is None or img5d.img is None):
# import image; will re-import over any existing image file
if os.path.isdir(path) and all(
[r is None for r in config.reg_suffixes.values()]):
# import directory of single plane images to single
# stack if no register suffixes are set
chls, import_md = importer.setup_import_dir(path)
add_metadata()
prefix = config.prefix
if not prefix:
prefix = os.path.join(
os.path.dirname(path),
importer.DEFAULT_IMG_STACK_NAME)
img5d = importer.import_planes_to_stack(
chls, prefix, import_md)
elif import_only:
# import multi-plane image
chls, import_path = importer.setup_import_multipage(
path)
prefix = config.prefix if config.prefix else import_path
import_md = importer.setup_import_metadata(
chls, config.channel, series)
add_metadata()
img5d = importer.import_multiplane_images(
chls,
prefix,
import_md,
series,
channel=config.channel)
if img5d is not None:
# set loaded main image in config
config.img5d = img5d
config.image5d = config.img5d.img
except FileNotFoundError as e:
_logger.exception(e)
_logger.info("Could not load %s", path)
if config.metadatas and config.metadatas[0]:
# assign metadata from alternate file if given to supersede settings
# for any loaded image5d
# TODO: access metadata directly from given image5d's dict to allow
# loading multiple image5d images simultaneously
importer.assign_metadata(config.metadatas[0])
# main image is currently required since many parameters depend on it
if fallback_main_img and atlas_suffix is None and config.image5d is None:
# fallback to atlas if main image not already loaded
atlas_suffix = config.RegNames.IMG_ATLAS.value
_logger.info(
"Main image is not set, falling back to registered image with "
"suffix %s", atlas_suffix)
# use prefix to get images registered to a different image, eg a
# downsampled version, or a different version of registered images
path = config.prefix if config.prefix else path
if path and atlas_suffix is not None:
try:
# will take the place of any previously loaded image5d
config.img5d = sitk_io.read_sitk_files(path,
atlas_suffix,
make_3d=True)
config.image5d = config.img5d.img
except FileNotFoundError as e:
print(e)
# load metadata related to the labels image
config.labels_metadata = labels_meta.LabelsMeta(
f"{path}." if config.prefix else path).load()
# load labels reference file, prioritizing path given by user
# and falling back to any extension matching PATH_LABELS_REF
path_labels_refs = [config.load_labels]
labels_path_ref = config.labels_metadata.path_ref
if labels_path_ref:
path_labels_refs.append(labels_path_ref)
labels_ref = None
for ref in path_labels_refs:
if not ref: continue
try:
# load labels reference file
labels_ref = ontology.LabelsRef(ref).load()
if labels_ref.ref_lookup is not None:
config.labels_ref = labels_ref
_logger.debug("Loaded labels reference file from %s", ref)
break
except (FileNotFoundError, KeyError):
pass
if path_labels_refs and (labels_ref is None
or labels_ref.ref_lookup is None):
# warn if labels path given but none found
_logger.warn(
"Unable to load labels reference file from '%s', skipping",
path_labels_refs)
if annotation_suffix is not None:
try:
# load labels image
# TODO: need to support multichannel labels images
img5d, config.labels_img_sitk = sitk_io.read_sitk_files(
path, annotation_suffix, True, True)
config.labels_img = img5d.img[0]
except FileNotFoundError as e:
print(e)
if config.image5d is not None:
# create a blank labels images for custom annotation; colormap
# can be generated for the original labels loaded below
config.labels_img = np.zeros(config.image5d.shape[1:4],
dtype=int)
print("Created blank labels image from main image")
if config.image5d is not None and config.labels_img is not None:
# set up scaling factors by dimension between intensity and
# labels images
config.labels_scaling = importer.calc_scaling(
config.image5d, config.labels_img)
if borders_suffix is not None:
# load borders image, which can also be another labels image
try:
config.borders_img = sitk_io.read_sitk_files(path,
borders_suffix,
make_3d=True).img[0]
except FileNotFoundError as e:
print(e)
if config.atlas_labels[config.AtlasLabels.ORIG_COLORS]:
labels_orig_ids = config.labels_metadata.region_ids_orig
if labels_orig_ids is None:
if config.load_labels is not None:
# load original labels image from same directory as ontology
# file for consistent ID-color mapping, even if labels are missing
try:
config.labels_img_orig = sitk_io.load_registered_img(
config.load_labels, config.RegNames.IMG_LABELS.value)
except FileNotFoundError as e:
print(e)
if config.labels_img is not None and config.labels_img_orig is None:
_logger.warn(
"Could not load original labels image IDs; colors may "
"differ from the original image")
load_rot90 = config.roi_profile["load_rot90"]
if load_rot90 and config.image5d is not None:
# rotate main image specified num of times x90deg after loading since
# need to rotate images output by deep learning toolkit
config.image5d = np.rot90(config.image5d, load_rot90, (2, 3))
if (config.image5d is not None and load_subimage
and not config.image5d_is_roi):
# crop full image to bounds of sub-image
config.image5d = plot_3d.prepare_subimg(config.image5d, offset,
size)[None]
config.image5d_is_roi = True
# add any additional image5d thresholds for multichannel images, such
# as those loaded without metadata for these settings
colormaps.setup_cmaps()
num_channels = get_num_channels(config.image5d)
config.near_max = libmag.pad_seq(config.near_max, num_channels, -1)
config.near_min = libmag.pad_seq(config.near_min, num_channels, 0)
config.vmax_overview = libmag.pad_seq(config.vmax_overview, num_channels)
colormaps.setup_colormaps(num_channels)
if config.labels_img is not None:
# make discrete colormap for labels image
config.cmap_labels = colormaps.setup_labels_cmap(config.labels_img)
if (blobs is not None and blobs.blobs is not None
and config.img5d.img is not None and blobs.roi_size is not None):
# scale blob coordinates to main image if shapes differ
scaling = np.divide(config.img5d.img.shape[1:4], blobs.roi_size)
# scale radius by mean of other dimensions' scaling
scaling = np.append(scaling, np.mean(scaling))
if not np.all(scaling == 1):
_logger.debug("Scaling blobs to main image by factor: %s", scaling)
blobs.blobs[:, :4] = ontology.scale_coords(blobs.blobs[:, :4],
scaling)
blobs.scaling = scaling
def detect_blobs_blocks(filename_base, image5d, offset, size, channels,
verify=False, save_dfs=True, full_roi=False,
coloc=False):
"""Detect blobs by block processing of a large image.
All channels are processed in the same blocks.
Args:
filename_base: Base path to use file output.
image5d: Large image to process as a Numpy array of t,z,y,x,[c]
offset: Sub-image offset given as coordinates in z,y,x.
size: Sub-image shape given in z,y,x.
channels (Sequence[int]): Sequence of channels, where None detects
in all channels.
verify: True to verify detections against truth database; defaults
to False.
save_dfs: True to save data frames to file; defaults to True.
full_roi (bool): True to treat ``image5d`` as the full ROI; defaults
to False.
coloc (bool): True to perform blob co-localizations; defaults to False.
Returns:
tuple[int, int, int], str, :class:`magmap.cv.detector.Blobs`:
Accuracy metrics from :class:`magmap.cv.detector.verify_rois`,
feedback message from this same function, and detected blobs.
"""
time_start = time()
subimg_path_base = filename_base
if size is None or offset is None:
# uses the entire stack if no size or offset specified
size = image5d.shape[1:4]
offset = (0, 0, 0)
else:
# get base path for sub-image
subimg_path_base = naming.make_subimage_name(
filename_base, offset, size)
filename_blobs = libmag.combine_paths(subimg_path_base, config.SUFFIX_BLOBS)
# get ROI for given region, including all channels
if full_roi:
# treat the full image as the ROI
roi = image5d[0]
else:
roi = plot_3d.prepare_subimg(image5d, offset, size)
num_chls_roi = 1 if len(roi.shape) < 4 else roi.shape[3]
if num_chls_roi < 2:
coloc = False
print("Unable to co-localize as image has only 1 channel")
# prep chunking ROI into sub-ROIs with size based on segment_size, scaling
# by physical units to make more independent of resolution; use profile
# from first channel to be processed for block settings
time_detection_start = time()
settings = config.get_roi_profile(channels[0])
print("Profile for block settings:", settings[settings.NAME_KEY])
sub_roi_slices, sub_rois_offsets, denoise_max_shape, exclude_border, \
tol, overlap_base, overlap, overlap_padding = setup_blocks(
settings, roi.shape)
# TODO: option to distribute groups of sub-ROIs to different servers
# for blob detection
seg_rois = StackDetector.detect_blobs_sub_rois(
roi, sub_roi_slices, sub_rois_offsets, denoise_max_shape,
exclude_border, coloc, channels)
detection_time = time() - time_detection_start
print("blob detection time (s):", detection_time)
# prune blobs in overlapping portions of sub-ROIs
time_pruning_start = time()
segments_all, df_pruning = StackPruner.prune_blobs_mp(
roi, seg_rois, overlap, tol, sub_roi_slices, sub_rois_offsets, channels,
overlap_padding)
pruning_time = time() - time_pruning_start
print("blob pruning time (s):", pruning_time)
#print("maxes:", np.amax(segments_all, axis=0))
# get weighted mean of ratios
if df_pruning is not None:
print("\nBlob pruning ratios:")
path_pruning = "blob_ratios.csv" if save_dfs else None
df_pruning_all = df_io.data_frames_to_csv(
df_pruning, path_pruning, show=" ")
cols = df_pruning_all.columns.tolist()
blob_pruning_means = {}
if "blobs" in cols:
blobs_unpruned = df_pruning_all["blobs"]
num_blobs_unpruned = np.sum(blobs_unpruned)
for col in cols[1:]:
blob_pruning_means["mean_{}".format(col)] = [
np.sum(np.multiply(df_pruning_all[col], blobs_unpruned))
/ num_blobs_unpruned]
path_pruning_means = "blob_ratios_means.csv" if save_dfs else None
df_pruning_means = df_io.dict_to_data_frame(
blob_pruning_means, path_pruning_means, show=" ")
else:
print("no blob ratios found")
'''# report any remaining duplicates
np.set_printoptions(linewidth=500, threshold=10000000)
print("all blobs (len {}):".format(len(segments_all)))
sort = np.lexsort(
(segments_all[:, 2], segments_all[:, 1], segments_all[:, 0]))
blobs = segments_all[sort]
print(blobs)
print("checking for duplicates in all:")
print(detector.remove_duplicate_blobs(blobs, slice(0, 3)))
'''
stats_detection = None
fdbk = None
colocs = None
if segments_all is not None:
# remove the duplicated elements that were used for pruning
detector.replace_rel_with_abs_blob_coords(segments_all)
if coloc:
colocs = segments_all[:, 10:10+num_chls_roi].astype(np.uint8)
# remove absolute coordinate and any co-localization columns
segments_all = detector.remove_abs_blob_coords(segments_all)
# compare detected blobs with truth blobs
# TODO: assumes ground truth is relative to any ROI offset,
# but should make customizable
if verify:
stats_detection, fdbk = verifier.verify_stack(
filename_base, subimg_path_base, settings, segments_all,
channels, overlap_base)
if config.save_subimg:
subimg_base_path = libmag.combine_paths(
subimg_path_base, config.SUFFIX_SUBIMG)
if (isinstance(config.image5d, np.memmap) and
config.image5d.filename == os.path.abspath(subimg_base_path)):
# file at sub-image save path may have been opened as a memmap
# file, in which case saving would fail
libmag.warn("{} is currently open, cannot save sub-image"
.format(subimg_base_path))
else:
# write sub-image, which is in ROI (3D) format
with open(subimg_base_path, "wb") as f:
np.save(f, roi)
# store blobs in Blobs instance
# TODO: consider separating into blobs and blobs metadata archives
blobs = detector.Blobs(
segments_all, colocalizations=colocs, path=filename_blobs)
blobs.resolutions = config.resolutions
blobs.basename = os.path.basename(config.filename)
blobs.roi_offset = offset
blobs.roi_size = size
# whole image benchmarking time
times = (
[detection_time],
[pruning_time],
time() - time_start)
times_dict = {}
for key, val in zip(StackTimes, times):
times_dict[key] = val
if segments_all is None:
print("\nNo blobs detected")
else:
print("\nTotal blobs found:", len(segments_all))
detector.show_blobs_per_channel(segments_all)
print("\nTotal detection processing times (s):")
path_times = "stack_detection_times.csv" if save_dfs else None
df_io.dict_to_data_frame(times_dict, path_times, show=" ")
return stats_detection, fdbk, blobs
def detect_blobs_large_image(filename_base, image5d, offset, size,
verify=False, save_dfs=True, full_roi=False):
"""Detect blobs within a large image through parallel processing of
smaller chunks.
Args:
filename_base: Base path to use file output.
image5d: Large image to process as a Numpy array of t,z,y,x,[c]
offset: Sub-image offset given as coordinates in z,y,x.
size: Sub-image shape given in z,y,x.
verify: True to verify detections against truth database; defaults
to False.
save_dfs: True to save data frames to file; defaults to True.
full_roi (bool): True to treat ``image5d`` as the full ROI; defaults
to False.
"""
time_start = time()
if size is None or offset is None:
# uses the entire stack if no size or offset specified
size = image5d.shape[1:4]
offset = (0, 0, 0)
else:
# change base filename for ROI-based partial stack
filename_base = make_subimage_name(filename_base, offset, size)
filename_subimg = libmag.combine_paths(filename_base, config.SUFFIX_SUBIMG)
filename_blobs = libmag.combine_paths(filename_base, config.SUFFIX_BLOBS)
# get ROI for given region, including all channels
if full_roi:
# treat the full image as the ROI
roi = image5d[0]
else:
roi = plot_3d.prepare_subimg(image5d, size, offset)
_, channels = plot_3d.setup_channels(roi, config.channel, 3)
# prep chunking ROI into sub-ROIs with size based on segment_size, scaling
# by physical units to make more independent of resolution
time_detection_start = time()
settings = config.roi_profile # use default settings
scaling_factor = detector.calc_scaling_factor()
print("microsope scaling factor based on resolutions: {}"
.format(scaling_factor))
denoise_size = config.roi_profile["denoise_size"]
denoise_max_shape = None
if denoise_size:
# further subdivide each sub-ROI for local preprocessing
denoise_max_shape = np.ceil(
np.multiply(scaling_factor, denoise_size)).astype(int)
# overlap sub-ROIs to minimize edge effects
overlap_base = chunking.calc_overlap()
tol = np.multiply(overlap_base, settings["prune_tol_factor"]).astype(int)
overlap_padding = np.copy(tol)
overlap = np.copy(overlap_base)
exclude_border = config.roi_profile["exclude_border"]
if exclude_border is not None:
# exclude border to avoid blob detector edge effects, where blobs
# often collect at the faces of the sub-ROI;
# ensure that overlap is greater than twice the border exclusion per
# axis so that no plane will be excluded from both overlapping sub-ROIs
exclude_border_thresh = np.multiply(2, exclude_border)
overlap_less = np.less(overlap, exclude_border_thresh)
overlap[overlap_less] = exclude_border_thresh[overlap_less]
excluded = np.greater(exclude_border, 0)
overlap[excluded] += 1 # additional padding
overlap_padding[excluded] = 0 # no need to prune past excluded border
print("sub-ROI overlap: {}, pruning tolerance: {}, padding beyond "
"overlap for pruning: {}, exclude borders: {}"
.format(overlap, tol, overlap_padding, exclude_border))
max_pixels = np.ceil(np.multiply(
scaling_factor,
config.roi_profile["segment_size"])).astype(int)
print("preprocessing max shape: {}, detection max pixels: {}"
.format(denoise_max_shape, max_pixels))
sub_roi_slices, sub_rois_offsets = chunking.stack_splitter(
roi.shape, max_pixels, overlap)
# TODO: option to distribute groups of sub-ROIs to different servers
# for blob detection
seg_rois = detect_blobs_sub_rois(
roi, sub_roi_slices, sub_rois_offsets, denoise_max_shape, exclude_border)
detection_time = time() - time_detection_start
print("blob detection time (s):", detection_time)
# prune blobs in overlapping portions of sub-ROIs
time_pruning_start = time()
segments_all, df_pruning = _prune_blobs_mp(
roi, seg_rois, overlap, tol, sub_roi_slices, sub_rois_offsets, channels,
overlap_padding)
pruning_time = time() - time_pruning_start
print("blob pruning time (s):", pruning_time)
#print("maxes:", np.amax(segments_all, axis=0))
# get weighted mean of ratios
if df_pruning is not None:
print("\nBlob pruning ratios:")
path_pruning = "blob_ratios.csv" if save_dfs else None
df_pruning_all = df_io.data_frames_to_csv(
df_pruning, path_pruning, show=" ")
cols = df_pruning_all.columns.tolist()
blob_pruning_means = {}
if "blobs" in cols:
blobs_unpruned = df_pruning_all["blobs"]
num_blobs_unpruned = np.sum(blobs_unpruned)
for col in cols[1:]:
blob_pruning_means["mean_{}".format(col)] = [
np.sum(np.multiply(df_pruning_all[col], blobs_unpruned))
/ num_blobs_unpruned]
path_pruning_means = "blob_ratios_means.csv" if save_dfs else None
df_pruning_means = df_io.dict_to_data_frame(
blob_pruning_means, path_pruning_means, show=" ")
else:
print("no blob ratios found")
'''# report any remaining duplicates
np.set_printoptions(linewidth=500, threshold=10000000)
print("all blobs (len {}):".format(len(segments_all)))
sort = np.lexsort(
(segments_all[:, 2], segments_all[:, 1], segments_all[:, 0]))
blobs = segments_all[sort]
print(blobs)
print("checking for duplicates in all:")
print(detector.remove_duplicate_blobs(blobs, slice(0, 3)))
'''
stats_detection = None
fdbk = None
if segments_all is not None:
# remove the duplicated elements that were used for pruning
detector.replace_rel_with_abs_blob_coords(segments_all)
segments_all = detector.remove_abs_blob_coords(segments_all)
# compare detected blobs with truth blobs
# TODO: assumes ground truth is relative to any ROI offset,
# but should make customizable
if verify:
db_path_base = None
exp_name = os.path.splitext(os.path.basename(config.filename))[0]
try:
if config.truth_db is None:
# find and load truth DB based on filename and subimage
db_path_base = os.path.basename(filename_base)
print("about to verify with truth db from {}"
.format(db_path_base))
sqlite.load_truth_db(db_path_base)
if config.truth_db is not None:
# truth DB may contain multiple experiments for different
# subimages; series not included in exp name since in ROI
rois = config.truth_db.get_rois(exp_name)
if rois is None:
# exp may have been named by ROI
print("{} experiment name not found, will try with"
"ROI offset/size".format(exp_name))
exp_name = make_subimage_name(exp_name, offset, size)
rois = config.truth_db.get_rois(exp_name)
if rois is None:
raise LookupError(
"No truth set ROIs found for experiment {}, will "
"skip detection verification".format(exp_name))
print("load ROIs from exp: {}".format(exp_name))
exp_id = sqlite.insert_experiment(
config.verified_db.conn, config.verified_db.cur,
exp_name, None)
verify_tol = np.multiply(
overlap_base, settings["verify_tol_factor"])
stats_detection, fdbk = detector.verify_rois(
rois, segments_all, config.truth_db.blobs_truth,
verify_tol, config.verified_db, exp_id, config.channel)
except FileNotFoundError:
libmag.warn("Could not load truth DB from {}; "
"will not verify ROIs".format(db_path_base))
except LookupError as e:
libmag.warn(str(e))
file_time_start = time()
if config.save_subimg:
if (isinstance(config.image5d, np.memmap) and
config.image5d.filename == os.path.abspath(filename_subimg)):
# file at sub-image save path may have been opened as a memmap
# file, in which case saving would fail
libmag.warn("{} is currently open, cannot save sub-image"
.format(filename_subimg))
else:
# write sub-image, which is in ROI (3D) format
with open(filename_subimg, "wb") as f:
np.save(f, roi)
# save blobs
# TODO: only segments used; consider removing the rest except ver
outfile_blobs = open(filename_blobs, "wb")
np.savez(outfile_blobs, ver=BLOBS_NP_VER, segments=segments_all,
resolutions=config.resolutions,
basename=os.path.basename(config.filename), # only save name
offset=offset, roi_size=size) # None unless explicitly set
outfile_blobs.close()
file_save_time = time() - file_time_start
# whole image benchmarking time
times = (
[detection_time],
[pruning_time],
time() - time_start)
times_dict = {}
for key, val in zip(StackTimes, times):
times_dict[key] = val
if segments_all is None:
print("\nNo blobs detected")
else:
print("\nTotal blobs found:", len(segments_all))
detector.show_blobs_per_channel(segments_all)
print("file save time:", file_save_time)
print("\nTotal detection processing times (s):")
path_times = "stack_detection_times.csv" if save_dfs else None
df_io.dict_to_data_frame(times_dict, path_times, show=" ")
return stats_detection, fdbk, segments_all